Software Engineer – Backend - India - Recurrent Software

Description

Company Description

Recurrent Software leads the way in leveraging the transformative potential of Generative AI and Machine Learning across various industries. Known for innovation, the company specializes in developing advanced solutions to tackle complex challenges. By combining deep domain expertise with cutting-edge technical capabilities, Recurrent Software delivers tailor-made tools that enhance efficiency, optimize resource usage, and unlock new insights from data. These solutions are designed to provide measurable value and support long-term growth across diverse sectors.

Role Description

We are a fast-moving startup building intelligent, AI-powered products that solve real-world problems. We are looking for a versatile Backend & AI Engineer who can wear two hats: designing robust, scalable backend services and architecting cutting-edge AI agent systems powered by large language models (LLMs). This is a 50/50 split role where you will spend half your time building reliable APIs, data pipelines, and database layers, and the other half creating autonomous AI agents, integrating LLMs, and working with vector databases.You will work directly with the founding team and have a meaningful impact on our product, architecture, and engineering culture from day one.

BACKEND ENGINEERING RESPONSIBILITIES (50%)

• Design, build, and maintain RESTful APIs using Python and FastAPI with a focus on performance, reliability, and clean contract design.
• Architect and optimize relational and non-relational database schemas (PostgreSQL, MongoDB, or similar) including indexing, query tuning, and migrations.
• Implement authentication, authorization, rate-limiting, and other API security best practices.
• Write comprehensive tests (unit, integration, end-to-end) and set up CI/CD pipelines for automated deployment.
• Build scalable microservices and background task systems using tools such as Celery, Redis, or message queues.
• Collaborate on infrastructure decisions including containerization (Docker), orchestration (Kubernetes), and cloud services (AWS, GCP, or Azure).
• Produce clear API documentation (OpenAPI / Swagger) and maintain well-structured, reviewable code.

AI & LLM AGENT ENGINEERING RESPONSIBILITIES (50%)

• Design and develop autonomous AI agents using frameworks such as LangGraph, LangChain, CrewAI, AutoGen, or similar tools.
• Integrate large language models (OpenAI, Anthropic, open-source models) into production workflows with prompt engineering, function/tool calling, and output parsing.
• Build and manage Retrieval-Augmented Generation (RAG) pipelines, including document ingestion, chunking strategies, embedding generation, and semantic search.
• Set up, configure, and optimize vector databases such as Pinecone, Weaviate, Qdrant, ChromaDB, or Milvus.
• Implement agent memory, multi-step reasoning, planning loops, and tool-use patterns for complex task completion.
• Evaluate and benchmark LLM outputs, iterate on prompt design, and monitor model performance and cost.
• Stay current with the rapidly evolving AI/LLM ecosystem and proactively bring new ideas, tools, and techniques to the team.

REQUIRED QUALIFICATIONS

• 3+ years of professional experience as a backend or software engineer, with strong proficiency in Python.
• Deep hands-on experience with FastAPI (or comparable frameworks like Flask/Django) and RESTful API design principles.
• Solid understanding of relational databases (PostgreSQL, MySQL) and NoSQL databases (MongoDB, DynamoDB) including schema design, indexing, and query optimization.
• Practical experience building LLM-based applications or AI agents using at least one framework (LangGraph, LangChain, CrewAI, Semantic Kernel, etc.).
• Working knowledge of at least one vector database (Pinecone, Weaviate, Qdrant, ChromaDB, Milvus, or pgvector).
• Understanding of embeddings, semantic search, and RAG architecture patterns.
• Comfort working in a fast-paced, ambiguous startup environment where priorities can shift quickly.
• Strong communication skills and ability to work effectively in a fully remote, asynchronous team.

NICE TO HAVE

• Experience with multi-agent orchestration and complex agentic workflows.
• Familiarity with fine-tuning or training LLMs and working with open-source models (LLaMA, Mistral, etc.).
• Knowledge of graph databases (Neo4j) or knowledge graph construction.
• Experience with event-driven architectures, streaming data, or real-time systems.
• Background in MLOps, model deployment, or inference optimization.
• Contributions to open-source AI/ML projects.

WHAT WE OFFER

• Competitive salary with meaningful equity in an early-stage startup.
• 100% remote work with flexible hours and async-first culture.
• Opportunity to shape architecture, product direction, and engineering practices.
• A small, talented team where your work has outsized impact.
• Learning budget and conference allowance to stay at the frontier of AI.
• Generous PTO and a culture that values sustainable pace.

HOW TO APPLY

Send your resume via LinkedIn application and a brief note describing a backend system and an AI/agent project you have built. Bonus points for links to GitHub repositories, blog posts, or demos. We review every application and aim to respond within one week.