AI Engineer

AI Engineer
About the Job
Company: Trida Labs
Location: Chennai, India
Employment Type: Full-time
Experience: 3–5 Years
About Trida Labs
Trida Labs builds AI-native products that help organizations work with enterprise data, analytics, and intelligent applications.
Our products include:
TridaPad — An AI-native data collaboration platform for querying, analyzing, visualizing, and managing data across SQL, NoSQL, Big Data, and cloud data sources.
AgentSQL — An agentic AI analytics solution that enables users to interact with enterprise data using natural language, generate SQL, perform analysis, create visualizations and dashboards, and derive insights.
TridaPad MCP Server — A Model Context Protocol server that enables AI assistants and MCP-compatible clients to interact with TridaPad and its data capabilities.
About the Role
We are looking for an AI Engineer to build and improve user-facing AI features across TridaPad and our AI-powered analytics products.
You will develop AI-assisted query experiences, SQL explanations and error assistance, chart and dashboard recommendations, and data-driven summaries and insights. You will work with LLMs, structured outputs, retrieval, evaluation, and product APIs to deliver useful and trustworthy user experiences.
The Data & AI team owns data connectivity, schema, metadata, and semantic foundations. The AI Agent team owns agent orchestration and behavior, while the NLP/ML team focuses on model and generation quality. This role applies these capabilities to reliable, user-facing AI product features.
What You'll Do
1. User-Facing AI Features
Build AI-powered features that help users query, understand, and work with enterprise data.
Develop SQL explanations, query suggestions, and SQL error assistance.
Build chart recommendations and AI-assisted dashboard layouts based on query results.
Generate plain-language summaries and explanations of analytical results.
Help users understand AgentSQL findings and analytical outputs.
Make AI-generated results useful, transparent, and easy to review.
2. LLM & AI Application Engineering
Design and develop production-ready applications using LLMs and Generative AI.
Integrate model providers based on application requirements.
Develop prompts, context strategies, structured outputs, and AI workflows.
Use typed and validated outputs in application features.
Improve accuracy, consistency, reliability, and performance.
Prefer deterministic application logic when an LLM adds limited value.
3. AI-Assisted Query & Analytics Experiences
Build workflows around natural-language queries, SQL, analysis, and visualization.
Present generated SQL clearly and allow users to review or edit it where appropriate.
Explain how analytical results were produced and connect insights to underlying query results.
Handle ambiguous or unsupported requests with useful clarification and fallback experiences.
4. Insight Generation & Numeric Grounding
Generate explanations, summaries, and insights from actual analytical results.
Ensure figures, percentages, totals, and trends are grounded in query results.
Validate generated summaries before presenting them to users.
Prevent unsupported numerical claims and conclusions.
Distinguish observed results, calculated metrics, and model-generated explanations.
Investigate cases where AI-generated insights misrepresent underlying data.
5. Context & Retrieval
Use schema, metadata, and semantic capabilities provided by the Data & AI layer.
Retrieve and assemble relevant context for user-facing AI workflows.
Apply RAG, embeddings, and vector databases where they provide product value.
Evaluate context relevance and sufficiency.
Collaborate with Data & AI engineers when additional metadata or context capabilities are required.
6. AI Tools & Agent Integration
Integrate AI features with APIs, application services, data tools, and existing product workflows.
Use tool and function calling where required.
Integrate with the TridaPad MCP Server where appropriate.
Collaborate with AI Agent engineers when new tools or orchestration capabilities are needed.
Avoid duplicating agent infrastructure owned by the AI Agent team.
7. AI Evaluation & Quality
Build evaluation datasets and test cases for user-facing AI features.
Evaluate correctness, relevance, consistency, and usability.
Test SQL explanations, summaries, insights, visualizations, and dashboard recommendations.
Verify that numerical claims are grounded in actual query results.
Test ambiguous, incomplete, and unsupported requests.
Identify recurring failures and investigate their root causes.
Compare prompts, models, context strategies, and workflow changes.
Establish repeatable evaluation and regression testing for production AI features.
8. AI User Experience & Trust
Design AI experiences that make generated outputs understandable and reviewable.
Provide traceability between insights and their underlying results.
Handle uncertainty and low-confidence situations without presenting unsupported conclusions as facts.
Design useful clarification, retry, and fallback experiences.
Collaborate with product and frontend engineers to integrate AI features into the user experience.
9. Performance & Optimization
Optimize AI features for quality, latency, reliability, and cost.
Reduce unnecessary model calls and token usage.
Improve prompt and context efficiency while maintaining output quality.
Evaluate model and workflow trade-offs.
Investigate performance issues and improve production AI performance.
10. Production AI Engineering
Deploy and support AI features across development, staging, and production environments.
Troubleshoot issues across AI, application, API, database, and service layers.
Analyze logs, errors, model responses, and workflow behavior to identify root causes.
Collaborate with platform engineers on monitoring, logging, tracing, and AI observability.
Improve reliability, scalability, performance, and maintainability.
Participate in production issue investigation and resolution.
11. Engineering & Product Collaboration
Work with Product, AI Agent, Data & AI, NLP/ML, Backend, Frontend, and Platform engineers.
Translate product requirements into practical AI solutions.
Contribute to technical design and architecture discussions.
Define interfaces between AI features and underlying data, agent, and platform capabilities.
Build reusable AI components and application services.
Document AI workflows, evaluations, technical decisions, and implementations.
Role Ownership
AI Engineer: Owns user-facing AI features, AI-assisted analytics, insight generation, AI UX, and application-level AI workflows.
Data & AI Engineer: Owns data connectivity, schema, metadata, semantic representations, and enterprise data context.
AI Agent Engineer: Owns agent orchestration, tools, agent workflows, and agent behavior.
ML/NLP Engineer: Owns model development, NLP capabilities, and generation quality.
AI Platform Engineer: Owns model infrastructure, deployment, observability, security, and platform reliability.
What We're Looking For
3–5 years of experience in AI engineering, software engineering, ML engineering, or a related field.
Strong proficiency in Python.
Hands-on experience building LLM-powered or Generative AI applications.
Experience integrating AI models with APIs, application services, tools, or data systems.
Strong understanding of prompt engineering, context engineering, and structured AI outputs.
Experience building production software and user-facing application features.
Understanding of RAG, embeddings, vector databases, or retrieval systems.
Experience evaluating and improving AI application quality.
Strong debugging, problem-solving, analytical, communication, and collaboration skills.
Preferred Qualifications
Experience with LangGraph, LangChain, LlamaIndex, or similar frameworks.
Experience with AI agents, tool/function calling, MCP, and AI assistant integrations.
Experience building AI-powered data or analytics applications.
Experience with natural-language-to-SQL or AI-assisted query experiences.
Experience with AI evaluation, regression testing, and quality measurement.
Experience with structured outputs and schema validation for LLM applications.
Experience optimizing model usage, latency, token consumption, and inference costs.
Experience with PostgreSQL, MySQL, SQL Server, Snowflake, BigQuery, Databricks, or MongoDB.
Experience with

Work arrangement
No