Senior Gen AI Engineer- Applied LLMs & Agentic AI

Mandatory Hiring Criteria:

• Location: Mumbai (Current residents or immediate relocators only)
• Joining Timeline: Immediate joiners only
• Note: If your notice period is 30 days or more, please skip this posting.

About the Role:

We're hiring a Senior Gen AI Engineer to design, build, and scale production-grade Generative AI and Agentic AI systems. As part of our strategic partnership with Antal International, this is a direct client FTE role offering immediate career growth.

Work Location: Mumbai ( Lower Parel/ Airoli)

Work Mode: Hybrid

Your Responsibilities:

• Design and deploy real-world GenAI applications (RAG systems, copilots, agentic workflows)
• Build applications using commercial APIs (OpenAI, Anthropic Claude, Google Gemini) and open-weight models (Llama, Mistral, DeepSeek)
• Build and orchestrate AI agents using agentic AI frameworks (tool calling, structured outputs, planning, routing, human-in-the-loop)
• Design memory and state-management patterns for agentic applications
• Architect robust retrieval pipelines using vector databases (Pinecone, Qdrant, Weaviate)
• Set up evaluation frameworks (LLM-as-a-judge, RAGAS) to monitor accuracy and reliability
• Deploy and operate AI services on cloud platforms (AWS, Azure, GCP) using Docker and CI/CD
• Write clean, modular, well-documented code while mentoring junior engineers

Must-Have Skills (Non-Negotiable):

• 4 to 7 years overall engineering, data science, ML, or AI experience
• 2 plus years deeply focused on building Gen AI applications for production
• Strong proficiency in Python and modern AI application development
• Real-world experience with RAG pipelines, chunking, embeddings, vector databases
• Solid understanding of LLM behavior (context-window management, hallucination mitigation, structured outputs)
• Hands-on experience with at least ONE agentic AI framework (LangGraph, CrewAI, LangChain, OpenAI Agents SDK, AWS Strands, AutoGen, Google ADK, PydanticAI, Semantic Kernel, etc.)
• Cloud deployment experience on at least one platform (AWS, Azure, or GCP)
• Clean coding, debugging, testing, API integration, prompt engineering fundamentals

Nice-to-Have Skills (Good to Have):

• Fine-tuning techniques (LoRA, QLoRA) and inference optimization • Model Context Protocol (MCP), agent-to-agent (A2A) patterns, guardrails
• Advanced multi-agent patterns (planner-executor, supervisor/router, human-in-the-loop workflows)
• Agent observability and evaluation frameworks

Location Preference : Willing to relocate to Mumbai only

Joining Timeline: Immediate hire preferred; Maximum 30 days notice period