Website:
thinkverge.in
Job details:
Role Overview
ThinkVerge is looking for a highly technical Senior / Lead AI Engineer to lead the development of production-grade Generative AI and Agentic AI systems for enterprise and government use cases.
This role is focused on building scalable AI applications beyond prototypes and demos, including:
- Enterprise AI copilots
- Multi-agent workflows
- RAG systems
- AI automation pipelines
- Intelligent workflow orchestration systems
The ideal candidate should have strong hands-on expertise in:
- LLMs & Agentic AI
- Scalable AI architecture
- Production AI deployment
- GCP AI ecosystem
- Backend engineering for AI systems
We are looking for someone who can independently architect, build, optimize, and deploy enterprise-scale AI systems end-to-end.
What You’ll Work On
- Multi-agent AI systems & orchestration workflows
- Enterprise AI copilots & conversational systems
- RAG pipelines & semantic retrieval systems
- Tool-calling & MCP integrations
- AI workflow automation systems
- AI observability & evaluation pipelines
- Scalable inference & model-serving systems
- Enterprise AI APIs & microservices
What We Expect You To Solve
- Hallucination reduction & response reliability
- Context and memory management in AI systems
- Multi-agent orchestration challenges
- Retrieval quality & ranking optimization
- Latency & token optimization
- AI workflow reliability & fallback handling
- Structured outputs & tool integrations
- Production scalability for AI workloads
- Enterprise-grade AI deployment challenges
- Cost optimization for large-scale inference systems
Required Skills
Generative AI / Agentic AI
- GPT / Gemini / Claude / Llama
- LangChain / LangGraph / CrewAI / AutoGen
- RAG architectures
- Prompt engineering
- AI agents & orchestration
- Tool calling & structured outputs
- Embeddings & vector search
- Fine-tuning / LoRA / PEFT
Backend & Infrastructure
- Python
- FastAPI
- REST APIs
- Async workflows
- PostgreSQL / Redis
- Kafka / PubSub
Cloud & AI Infrastructure
Strong hands-on experience with:
- GCP (mandatory)
- Vertex AI
- GKE / Kubernetes
- Docker
- GPU inference workloads
- MLOps / LLMOps
- CI/CD pipelines
Vector Databases
- Pinecone
- Weaviate
- pgvector
- FAISS
- ChromaDB
Experience
- 5–8 years overall engineering experience
- Strong production experience building GenAI systems
- Experience building scalable AI systems beyond POCs/demos
- Experience leading AI projects or teams preferred
Good To Have
- AI observability tools (Langfuse, Helicone, Arize)
- MCP / A2A integrations
- Distributed inference experience
- Open-source contributions
- Startup experience
Why Join ThinkVerge
- Build enterprise-scale Agentic AI systems
- Work on real-world enterprise and government AI deployments
- High ownership and technical leadership opportunity
- Opportunity to shape the AI engineering division from the ground up
Tech Stack
- Python | FastAPI | LangGraph | CrewAI | LangChain | Vertex AI | Gemini APIs | Kubernetes | GCP | Docker | PostgreSQL | Redis | Vector DBs
Click on Apply to know more.