AI/ML Engineer

About NowOnline Tech India Pvt. Ltd.
We are a dynamic and fast-growing technology firm building production-grade generative AI and agentic systems. Our team is passionate about shipping real products powered by large language models, multi-agent workflows, and cutting-edge AI research, while reasoning carefully about how these systems behave in the real world.
Position Overview:
Designation: AI/ML Engineer (Generative AI & AI Agents)
Type: Full-time
Experience Required: 2-3 years
Location: GIFT City, Gandhinagar (On-site)
Compensation: Best in the industry.
About the Role
We are looking for an experienced AI/ML Engineer to take ownership of core generative AI and agentic systems initiatives. You will design, build, and ship production-grade GenAI features and multi-agent workflows, working closely with the AI/ML team and cross-functional stakeholders on live products. This is a hands-on role for someone who has already shipped GenAI features in production, can make independent architectural decisions, and enjoys mentoring junior engineers while reasoning carefully about how LLMs behave in the wild.
Key Responsibilities
Design, build, and own generative AI features end to end, including prompting, retrieval-augmented generation (RAG), structured output generation, and evaluation
Architect and lead development of AI agents and multi-agent workflows that use tools, call APIs, and complete multi-step tasks reliably at production scale
Design and refine prompts, system instructions, and agent guardrails to improve accuracy, safety, and consistency, and set best practices for the team
Own the vector database and embeddings strategy for semantic search and context retrieval across products
Build and maintain evaluation harnesses to measure quality, latency, and cost, and drive systematic tuning and optimisation
Integrate LLM capabilities into backend services and APIs, with attention to scalability, reliability, and cost efficiency
Review the work of junior engineers and interns, and mentor them on GenAI and agentic system design
Document findings, experiments, and design decisions clearly for the team and stakeholders
Stay current with developments in generative AI, agentic frameworks, and industry best practices, and evaluate their fit for our stack
Collaborate closely with product, engineering, and leadership to translate business requirements into technical solutions
Required Skills & Knowledge
Core Engineering & LLM Knowledge
Strong Python skills with a track record of writing clean, modular, production-quality code
Solid, applied understanding of core LLM concepts: tokens, context windows, prompting, embeddings, RAG, and fine-tuning
Strong understanding of REST APIs and experience integrating external services in production systems
Proven ability to debug ambiguous LLM behaviour systematically and independently
Generative AI & Agents (Hands-On)
2-3 years of hands-on experience building and shipping generative AI features or products in a professional setting
Practical experience with at least one agent or LLM framework (e.g., LangChain, LlamaIndex, agent SDKs, or equivalent) in production
Strong understanding of prompt engineering, system instructions, and agent guardrail design
Demonstrated experience structuring and shipping reliable multi-step, tool-using workflows
Technical Tools & Technologies
Hands-on experience with vector stores (e.g., Postgres/pgvector, Pinecone, Qdrant) and orchestration patterns
Experience with Docker, job queues, or async task processing in production environments
Solid backend service development and API integration experience
Local LLM inference experience (e.g., Ollama, LM Studio) is a plus
LLM Safety & Reliability
Working knowledge of LLM safety topics such as prompt injection, jailbreak defenses, and output validation
Experience with evaluation methods for measuring quality, latency, and cost, and using them to drive decisions
Good to Have
Expertise in the Claude ecosystem: Claude API, Claude Code, the Claude Agent SDK, MCP (Model Context Protocol) servers, Skills, and prompt caching
Experience building and operating multi-agent or tool-using systems in production settings
Experience leading or mentoring junior engineers on GenAI projects
Contributions to open-source AI/ML projects or technical blog posts demonstrating expertise
Soft Skills
Strong analytical and problem-solving abilities, with sound independent judgement
Excellent written and verbal communication skills
Ability to lead initiatives, mentor others, and work effectively across teams
Attention to detail and ability to document findings clearly
Curiosity, fast self-learning, and a genuine passion for generative AI and emerging technologies
Educational Qualifications
BE/B.Tech in Computer Science, Information Technology, Artificial Intelligence, Data Science, or a related field
BCA or MCA graduates with strong, demonstrated experience in AI/ML and generative AI
Equivalent practical experience and a strong portfolio will be considered in lieu of formal qualifications
What We Offer
Ownership of real features and initiatives within a modern GenAI and agentic stack used in production
Opportunity to shape technical direction and mentor a growing AI/ML team
Compensation that is best in the industry, based on experience and skill assessment
Continuous learning and skill development in generative AI and agentic systems
A clear path for career growth within the organisation
Flexible work environment with on-site collaboration
What We Value in Candidates
Genuine curiosity and passion for generative AI and agentic systems
A track record of shipping and owning production GenAI features
Strong work ethic and commitment to professional excellence
Ability to work collaboratively and lead within a team environment
Proactive approach to problem-solving and finding innovative solutions
How to Apply
Email: hr@nowonlinetech.com
Phone: +91 7600235007
Website: www.nowonline.com

Work arrangement
No