Lead Gen AI & Agentic AI Engineer

Experience: 5+ years
Primary Stack: Python, LLM APIs, RAG, agent frameworks
Cloud: Cloud-agnostic. Deep experience with at least one of AWS, GCP, or Azure, and the ability to work on the others
Location & Mode: Full-time, Work From Office. Noida, Sector 132
Company: Binariq (TSCx Consulting Pvt Ltd)
Role Summary
We are looking for a Lead Gen AI & Agentic AI Engineer to own the design and delivery of LLM-powered and autonomous agent systems for enterprise clients. You will take a business problem from an early client conversation through to a production system, making the architecture calls along the way and defending them to both technical and non-technical audiences.
We need someone who has built agents that run against live client systems. That means scoping what an agent can access, deciding where a human has to approve, and handling failures predictably when it acts.
Developing the engineers around you is a core part of this role. You will mentor associate engineers day to day, assist in running Binariq's internal training on Gen AI and agentic practice, and own the technical onboarding path for engineers joining the practice.
Key Responsibilities
Design & Build
Own end-to-end design of Gen AI solutions: retrieval architecture, model selection, prompt strategy, and integration approach
Design agentic systems: tool contracts, orchestration logic, state management, and multi-agent decomposition where it is justified
Define the boundaries of autonomy: what an agent may access, what it may act on, where a human must approve, and how it escalates
Build guardrails against prompt injection, sensitive data exposure, and unsafe or incorrect output
Design failure behaviour explicitly: retries, timeouts, circuit breakers, cost ceilings, and rollback paths
Establish evaluation frameworks for LLM and agent output, and use them to drive iteration rather than relying on impressions
Treat token and inference cost as a first-class design constraint
Client & Delivery
Work directly with client stakeholders to shape requirements and explain technical trade-offs
Support pre-sales and solutioning by estimating effort, assessing feasibility, and identifying risk early
Set technical direction on engagements and review the team's work against it
Hand over production-ready systems with the necessary instrumentation and documentation
Training & Capability Building
Mentor associate engineers through code review, pairing, and design discussion
Assist in executing Binariq's internal training on Gen AI and agentic engineering
Own the technical onboarding path for engineers joining the practice, so new joiners reach useful output quickly
Set and enforce engineering standards across the team, covering evaluation, guardrails, and safe agent design
Build reusable patterns, reference implementations, and internal documentation the team can work from
Required Technical Skills
Programming & Architecture
Strong Python, including asynchronous programming, packaging, and testing discipline
FastAPI or equivalent, with sound API and microservices design
SQL and NoSQL, with judgement about which fits a given problem
System design: how the AI components sit within a wider client architecture
Generative AI (depth expected)
Production experience with multiple LLM providers, and informed opinions about their trade-offs
Advanced RAG: chunking strategy, embedding model selection, hybrid and semantic search, re-ranking, query rewriting, and diagnosing retrieval failure
Vector databases: practical experience, including indexing strategy and retrieval performance at scale
Prompt and context engineering at system level, not just per call
Evaluation methodology: designing test sets, measuring groundedness and accuracy, and building regression suites for non-deterministic output
Guardrails and safety: prompt injection defence, output filtering, PII handling in prompts
LangChain / LlamaIndex, with a clear view of when not to use a framework
Agentic AI (the core of this role)
Tool and function calling: designing tool contracts, schemas, and error semantics
Production experience with at least one agent framework: LangGraph, CrewAI, AutoGen, Semantic
Kernel, Google ADK, or equivalent
Orchestration and state management across long-running, multi-step workflows
Agent memory: short-term context and persistent state
Human-in-the-loop design: approval gates, escalation, and deciding where autonomy should stop
Permissioning and sandboxing: scoping agent access to systems and data
Failure recovery and loop control: preventing runaway execution and runaway cost
Tracing and observability for agent runs (Langfuse, LangSmith, Arize Phoenix, or similar)
MCP (Model Context Protocol)
Multi-agent architecture, and the judgement to know when a single agent is the better answer
Cloud
Deep hands-on experience with at least one of:
AWS: Bedrock, SageMaker, Lambda
GCP: Vertex AI, Cloud Run
Azure: Azure OpenAI, Azure AI Search, Azure ML
Ability to become productive on the others, since client stacks vary
IAM, secrets management, and cloud security fundamentals
Docker, and enough CI/CD literacy to hand over cleanly
Good to Have
Fine-tuning open-source models (LoRA, PEFT, QLoRA) and a view on when fine-tuning beats retrieval
Lightweight AI/ML Ops exposure: enough monitoring to know when something has broken in production
Self-hosted and open-weight deployment (vLLM, Ollama, Hugging Face), relevant for data residency and air-gapped clients
Multi-modal systems: document, image, or voice
Classic predictive ML, for engagements that combine it with Gen AI
Regulated-domain delivery experience (BFSI, healthcare, public sector, defence)
Consulting or client-facing delivery background
Conference talks, published writing, or open-source contribution
Experience Requirements
5+ years of overall software engineering experience
3+ years hands-on with Gen AI or LLM-based application development
Hands-on agentic build experience: a system that called tools and took real actions across services, rather than one that only generated text. Production deployment with real users is strongly preferred; a substantial internal or proof-of-concept build will be considered where the candidate can explain the permissioning model, the failure handling, and what they would change to take it to production
Demonstrable ownership of architecture decisions, including ones that turned out to be wrong and what you changed
Experience working directly with business stakeholders
Demonstrable experience developing other engineers, through mentoring, technical leadership, or running training. Experience building a curriculum or onboarding programme is a strong advantage
What We're Looking For
Architecture judgement. Knowing when a simple RAG pipeline beats an agent, and being willing to say so to a client who asked for an agent.
Commitment to developing others. Raising the level around you is part of the role, not an extra. We are building a practice, and the team's depth matters as much as any single engagement.
Caution with autonomy. Understanding the risk of letting an agent act on a client's live systems, and designing for it.
Evaluation discipline. Measuring output quality with test sets and defined metrics.
Portable fundamentals. Our work spans different clients, clouds, and constraints. We look for people who understand how things work underneath, so their skills transfer.
Clear communication. You will explain technical limitations and trade-offs to client stakeholders who do not share your background.
Notes on Scope
This is a build role, not a platform role. Owning client production infrastructure, platform monitoring, and cost governance at scale is not what we are hiring for. That said, you should be comfortable deploying and running your own work, and you are expected to instrument and document your systems properly.

Work arrangement
No