? We’re Hiring | Applied AI Engineer

Are you passionate about turning LLMs and Generative AI into real-world, production-ready applications?

We’re looking for an Applied AI Engineer who can build scalable RAG pipelines, agentic AI workflows, LLM-powered APIs, and intelligent backend systems.

If you enjoy working with LangGraph, LangChain, Python, FastAPI, OpenAI, Gemini, and modern AI architectures, this could be a great chance to build impactful AI solutions. ?

? Mandatory Skill Set✅ Python

✅ FastAPI

✅ LangGraph

✅ LangChain

✅ Any one: Vector Databases / Embeddings / Semantic Search

✅ RAG Pipelines

✅ Agentic AI Workflows

✅ LLMs

✅ OpenAI

✅ Google Gemini

✅ Context Engineering

✅ Document Processing

✅ OCR

✅ Model Evaluation

? What You’ll Work On• Integrate LLMs into production applications, APIs, and backend systems

- Design and build scalable RAG architectures and retrieval pipelines
- Work with embeddings, vector search, semantic search, chunking, retrieval, and reranking
- Build agentic AI workflows using LangGraph, Google ADK, LangChain, or similar frameworks
- Develop multi-step, stateful, tool-using AI agents
- Integrate AI agents with APIs, databases, enterprise systems, and external tools
- Build production-grade AI APIs and microservices using Python/FastAPI
- Work on document processing and OCR-based AI solutions
- Implement effective prompt and context engineering strategies
- Evaluate and improve LLM and AI-agent accuracy, reliability, and response quality
- Optimize AI applications for latency, scalability, reliability, and cost
- Debug and troubleshoot complex issues across backend systems, APIs, LLMs, RAG pipelines, and agent workflows
- Collaborate with Product, Frontend, Data,



and Engineering teams to turn ideas into production-ready AI solutions

? What We’re Looking For
- Strong hands-on experience building production-grade LLM applications
- Solid understanding of RAG, embeddings, semantic search, vector retrieval, and document processing
- Experience building agentic AI systems and workflow orchestration
- Strong Python development skills with FastAPI
- Experience with OpenAI, Google Gemini, or similar LLM APIs
- Strong understanding of tool/function calling, state management, and AI workflow orchestration
- Experience with vector technologies such as Pinecone, FAISS, Chroma, Weaviate, Milvus, or similar
- Strong debugging, analytical, and problem-solving skills
- Ability to write clean, scalable, maintainable, and high-performance code

⭐ Good to Have• Google ADK / LangGraph / LangChain / LlamaIndex
- GCP, AWS, or Azure
- Vertex AI / Amazon Bedrock / Azure OpenAI
- LLM evaluation, observability, tracing, and monitoring
- AI guardrails and hallucination mitigation
- Docker, Git & CI/CD
- REST APIs & asynchronous programming
- Databases, caching, message queues & distributed systems
- Production security, authentication & authorization
- Experience deploying and operating production-grade GenAI applications

? The OpportunityThis is a hands-on engineering role where you’ll help build AI products that move beyond prototypes into reliable, scalable production systems.

If you’re excited about LLMs, RAG, AI agents, and building the backend infrastructure behind next-generation AI applications, we’d love to hear from you!

[email protected]

#Hiring #AppliedAI #AIEngineer #GenerativeAI #GenAI #LLM #RAG #AgenticAI #AI #MachineLearning #Python #FastAPI #LangGraph #LangChain #OpenAI #GoogleGemini #VectorDatabase #SemanticSearch #Embeddings #OCR #AIJobs #TechJobs #HiringNow

📌 Applied AI Engineer (Mumbai)
🏢 Softkode Technologies
📍 Mumbai