Software Engineer (AI/ML + Python)
Explicitly mentions vibe coding and AI-assisted development—uses tools like Cursor, Claude Code, Copilot for rapid prototyping and delivery.
About the Role
Forward Deployed Software Engineer role to design, build, and deploy production-grade AI systems using Python and modern LLM infrastructure. The position is customer-facing, combining backend engineering, agentic AI workflows, retrieval/RAG systems, and rapid prototyping to deliver reliable operational AI solutions.
Job Description
Role
We are hiring a Python / Forward Deployed Engineer to build and deploy production-grade AI systems for real-world business operations. This customer-facing role combines backend engineering, AI implementation, and rapid product delivery; you will work with customers, founders, and internal teams to design, build, deploy, and iterate AI-powered systems.
Key Responsibilities
- Work directly with customers to understand workflows, identify automation opportunities, and translate ambiguous requirements into production-ready AI systems.
- Design and implement agentic workflows, tool-using agents, multi-step reasoning pipelines, and autonomous task execution systems.
- Build production-ready RAG systems with optimized retrieval and context orchestration, including structured outputs, memory handling, function/tool calling, and fallback strategies.
- Develop scalable backend services using Python and FastAPI, design clean APIs, and integrate external APIs, enterprise systems, databases, and automation platforms.
- Containerize and deploy services (Docker, cloud), implement logging/monitoring/tracing, and maintain production reliability, scalability, and security.
- Rapidly prototype and iterate using AI-assisted development workflows and deliver operationally stable systems rather than demo prototypes.
Requirements
Required
- 2+ years of relevant experience.
- Strong Python engineering skills; experience with FastAPI and backend development.
- Experience with LLM APIs (OpenAI, Anthropic, Bedrock or similar) and agentic AI workflows.
- Experience building RAG pipelines and using vector databases (FAISS, Pinecone, Weaviate, MongoDB Atlas Vector Search, etc.).
- Prompt engineering, structured generation, memory handling, and techniques to control hallucinations and inference cost.
- Docker and cloud deployment experience; Git and software engineering fundamentals.
- Strong debugging skills, systems thinking, customer communication, and ability to own delivery end-to-end.
Good to have
- LangChain, LangGraph, LlamaIndex experience.
- Async Python and distributed systems experience.
- Kubernetes, CI/CD, observability tooling, and workflow orchestration systems.
- Experience with PostgreSQL, MongoDB, Redis, event-driven architectures, multi-agent systems, or voice/multimodal AI systems.
Experience & Reporting
- Experience: 2+ years.
- Payroll: Gray Matrix; Client Location: Dwarka, Delhi.
- Reporting to: Team Lead.
Work Location
- In person (on-site).
Benefits
- Health insurance
- Provident Fund