LogicHive Solutions is looking for a highly skilled Software Engineer II – AI Engineer with strong expertise in Python backend development, Generative AI, LLM applications, and AI agent engineering.

We are seeking an experienced engineer with 5+ years of software engineering experience and hands-on expertise in building and deploying production-grade AI-powered applications. The ideal candidate should have strong experience with LLM integration, Model Context Protocol (MCP), Retrieval-Augmented Generation (RAG), agent orchestration, and AI evaluation frameworks.

The role involves building intelligent AI solutions, backend services, data pipelines, and React-based interfaces, with a strong focus on developing reliable, secure, explainable, and auditable AI applications for enterprise workflows.

The engineer will work on end-to-end AI features, from prompt and agent design to API development, database integration, evaluation, and user interface implementation.

Key Responsibilities

- AI & LLM Application Development

- Build and maintain LLM-powered applications for document analysis, information extraction, evidence assessment, question answering, and workflow automation.
- Integrate Large Language Models from providers such as OpenAI, Anthropic, and Google Gemini.
- Implement prompt engineering, structured outputs, JSON schema validation, and function calling.
- Develop AI-powered features that generate reliable, evidence-based, and explainable outputs.
- Build solutions that support human review and validation of AI-generated results.

2. Agent Development & Orchestration
- Design and develop AI agents capable of using tools, retrieving relevant information, and executing multi-step workflows.
- Implement agent orchestration using frameworks such as LangChain, LangGraph, LlamaIndex, or similar.
- Develop tool execution, state management, validation, and human-in-the-loop workflows.
- Build conversational agents that support enterprise workflows and business processes.

3. MCP & Enterprise Tool Integration
- Build, integrate, and maintain Model Context Protocol (MCP) servers, clients, and tools.
- Connect AI applications and agents with internal enterprise systems and external services.
- Implement authentication, authorization, access controls, input validation, and error handling.
- Develop secure and reliable integrations for enterprise AI applications.

4. RAG & Retrieval Engineering
- Design and develop Retrieval-Augmented Generation (RAG) workflows.
- Implement document processing, chunking, embeddings, and vector or hybrid search.
- Work with vector databases and semantic retrieval techniques.
- Build source-grounded AI responses with proper document attribution and traceability.
- Optimize retrieval relevance and response accuracy.

5. Python Backend Development & APIs




- Develop scalable backend services using Python.
- Build REST APIs and backend integrations using FastAPI or Flask.
- Work with Pydantic, asynchronous programming, and structured data processing.
- Develop backend services supporting model interactions, retrieval, and agent execution.
- Implement robust API integrations and structured AI outputs.

6. AI Evaluation, Reliability & Observability
- Create evaluation datasets using human-labeled ground truth.
- Measure extraction accuracy, retrieval relevance, groundedness, and task completion.
- Implement LLM-as-judge evaluation techniques using multiple models.
- Develop regression testing processes for prompt, model, and retrieval changes.
- Implement logging, monitoring, retries, fallback mechanisms, and agent tracing.
- Ensure reliability and consistency of AI applications in production environments.

7. Security, Auditability & Collaboration
- Implement secure data-handling practices for enterprise AI applications.
- Maintain traceability of source evidence, model outputs, tool actions, and human review decisions.
- Collaborate with business stakeholders and cross-functional engineering teams to identify AI use cases.
- Translate business requirements into practical AI solutions and define acceptance criteria.
- Communicate AI capabilities, limitations, and evaluation results to technical and non-technical stakeholders.

Required Technical Skills
- AI & Generative AI
- Strong hands-on experience building and deploying production-grade LLM applications.
- Experience with OpenAI, Anthropic, or Google Gemini APIs.
- Prompt engineering, structured outputs, JSON schema validation, and function calling.
- Experience implementing LLM-powered enterprise applications.
- MCP & AI Agent Development
- Hands-on experience building and integrating Model Context Protocol (MCP) servers, clients, and tools.
- Understanding of authentication, access controls, and enterprise system integrations.
- Experience with LangChain, LangGraph, LlamaIndex, or similar agent orchestration frameworks.
- Knowledge of multi-step workflows, tool execution, and state management.
- RAG & Retrieval
- Experience developing Retrieval-Augmented Generation systems.
- Knowledge of document processing, chunking, embeddings, and vector databases.
- Experience with semantic search, hybrid search, and source-grounded responses.
- Python & Backend Engineering
- Strong proficiency in Python.
- Experience with FastAPI or Flask.




- Knowledge of Pydantic and asynchronous programming.
- Strong understanding of REST APIs and backend service development.
- Experience writing clean, modular, maintainable, and production-ready code.
- AI Evaluation & Engineering Quality
- Experience creating labeled evaluation datasets and defining evaluation metrics.
- Knowledge of LLM-as-judge and AI regression testing.
- Experience with pytest, logging, monitoring, retries, and fallback handling.
- Understanding of AI observability and production reliability.
- Preferred Qualifications
- Experience in finance, financial risk management, SOX compliance, internal audit, or controls automation.
- Experience processing complex PDFs, scanned documents, tables, and enterprise evidence using OCR or document AI.
- Familiarity with LLM observability, evaluation frameworks, and production monitoring.
- Experience with cloud deployment, containers, and CI/CD practices.
- Experience integrating AI applications with enterprise knowledge repositories, ticketing systems, and compliance platforms.
- Prior experience at Uber or familiarity with its internal developer ecosystem, data pipelines, and AI platforms.

Technology Stack

Category Technologies

- AI & LLM OpenAI, Google Gemini, Anthropic, Prompt Engineering, Structured Outputs
- Agents & MCP Model Context Protocol, LangChain, LangGraph, LlamaIndex
- RAG & Retrieval Embeddings, Vector Databases, Semantic Search, Hybrid Search
- Backend Python, FastAPI, Flask, Pydantic, REST APIs
- Document Processing pandas, PDF Parsing, OCR, Information Extraction
- Integrations GRC Platforms, Jira, Google Workspace APIs
- Testing & Observability pytest, AI Evaluation Frameworks, Agent Tracing, Logging, Monitoring
- Developer Tools Cursor, Claude Code, GitHub Copilot
- Qualifications & Experience
- Minimum 5+ years of professional software engineering experience.
- Strong hands-on expertise in Python and backend application development.
- Proven experience building and deploying production-grade LLM-powered applications.
- Practical experience with MCP servers, clients, and enterprise tool integrations.
- Strong understanding of RAG architectures, embeddings, vector search, and AI agent orchestration.
- Experience with FastAPI or Flask, Pydantic, asynchronous programming, and REST APIs.
- Practical experience with AI evaluation, testing, and production monitoring.
- Excellent problem-solving, analytical, and debugging skills.
- Ability to work independently and collaborate effectively with cross-functional teams.
- Strong communication skills and ability to explain technical concepts to business stakeholders.

Position Details Position: Software Engineer II – AI Engineer (Full Stack, Backend-Focused)

Experience: 5+ Years

Location: Bangalore, Pune
- Employment Type: Full time/Contract

📌 Software Engineer II – AI Engineer (Full Stack, Backend-Focused) (Bengaluru)
🏢 LogicHive®
📍 Bengaluru