Locations: Bangalore & Kochi, India
Company: Fospe Software Private Limited
Department: AI Product Engineering

Fospe is seeking a highly skilled LLM Engineer to build, optimize, and deploy next-generation AI applications powered by Large Language Models (LLMs). This role focuses on AI agents, RAG systems, prompt engineering, model optimization, and enterprise AI solutions.

Role Overview

As an LLM Engineer, you will design and develop AI-powered products using Anthropic Claude, OpenAI, Gemini, and open-source LLMs. You will work on AI agents, enterprise automation, knowledge systems, and advanced AI workflows.

Key Responsibilities

LLM Development

- Design and implement LLM-powered applications.
- Build AI assistants, AI agents, and conversational systems.
- Integrate Anthropic Claude, OpenAI, Gemini, and open-source models.
- Develop advanced prompt engineering strategies.

RAG & Knowledge Systems

- Build Retrieval-Augmented Generation (RAG) architectures.
- Implement vector search and semantic retrieval solutions.
- Design enterprise knowledge bases and AI search systems.
- Optimize retrieval accuracy and response quality.

AI Agent Engineering

- Develop autonomous and multi-agent systems.
- Implement tool calling, memory, planning, and reasoning capabilities.
- Build AI employees for sales, customer service, onboarding, and operations.
- Integrate AI agents with external APIs and enterprise applications.

Model Optimization

- Optimize token consumption and inference costs.
- Implement model selection and routing strategies.
- Improve latency, scalability, and reliability.
- Monitor AI performance and production metrics.





Backend & Integration

- Develop AI services using Python.
- Build REST APIs and AI microservices.
- Integrate AI systems with web, mobile, and enterprise platforms.
- Collaborate with product and engineering teams on deployment.

Required Skills

✅ Strong Python development experience

✅ Experience with Anthropic Claude API and/or OpenAI API

✅ Prompt Engineering

✅ RAG Architecture

✅ Vector Databases (Pinecone, Qdrant, Weaviate, Chroma)

✅ API Development

✅ Git & GitHub

✅ Strong problem-solving skills

Preferred Skills

- LangGraph

- LangChain

- CrewAI

- AutoGen

- MCP (Model Context Protocol)

- Docker & Kubernetes

- AWS, Azure, or GCP

- AI Evaluation Frameworks

- Fine-tuning and model customization

- Workflow Automation Platforms

What You’ll Build

- AI Agents & AI Employees
- Enterprise Knowledge Systems
- AI-Powered SaaS Products
- Customer Support Agents
- AI Sales Agents
- Research & Analysis Assistants
- Workflow Automation Platforms
- Multi-Agent Business Systems

Ideal Candidate

- 2+ years of software engineering experience.
- Experience building production AI applications.
- Strong understanding of modern LLM architectures and AI workflows.
- Passion for AI innovation and problem-solving.
- Ability to convert business requirements into scalable AI solutions.

What We Offer

✔ Competitive salary package

✔ Prospect to work on cutting-edge AI technologies

✔ Global customer exposure

✔ Career growth in AI Product Engineering

✔ Flexible and innovation-driven work environment

Job Category: Software

Job Type: Full Time

Job Location: Bangalore Cochin

📌 LLM Engineer (Large Language Models) (India)
🏢 Fospe
📍 India