Cognilium AI is a production-first AI product engineering company building reliable, scalable AI systems for startups and enterprises. Founded in 2019, we specialize in agentic AI, enterprise-grade RAG/NL2SQL, voice AI, and cloud-native data platforms—engineered for real users, real scale, and measurable ROI.

We focus on shipping AI that works in production, not demos. With 100+ AI projects, 50+ production GenAI deployments, 99.9% uptime, and 300%+ average ROI, our work is defined by reliability, performance, and outcomes.

We operate as a remote-first, AWS-centric team with a builder-led culture. Our engineers own systems end-to-end—from architecture and implementation to deployment, observability, and optimization.

AI only matters when it works. That's what we build.

The Role:

We're hiring an AI & Backend Engineer to build and scale production-grade AI systems—not prototypes.

You'll design, implement, and operate LLM-powered backend services using Python and FastAPI, working on agentic workflows, RAG systems, and AI-driven APIs that are used in real production environments. This is a hands-on role with end-to-end ownership, from system design to deployment and optimization.

You'll work closely with product and engineering teams to turn business problems into reliable, scalable AI solutions, with a strong focus on performance, cost control, and operational stability.

If you enjoy shipping AI that actually runs in production—and taking ownership beyond just writing code—this role is built for you.

Key Responsibilities:

Build AI-Powered Systems:

• Design, build, and deploy end-to-end generative AI applications

• Implement LLM-powered workflows, including agentic and multi-step reasoning systems

• Develop enterprise-grade RAG pipelines with grounding, citations, and guardrails

Backend & API Engineering:

• Build high-performance, asynchronous APIs using Python and FastAPI

• Design scalable microservices to expose AI capabilities

• Implement authentication, rate limiting, background jobs, and service boundaries

LLM Integration & Prompt Engineering:

• Integrate LLMs from OpenAI, Anthropic, and open-source providers

• Design prompts that minimize hallucinations and control latency and cost

• Work with vector databases to power retrieval and semantic search

System Architecture & Reliability:

• Collaborate on system architecture with a production-first mindset

• Design for scalability, fault tolerance, and security

• Implement observability, structured logging, and monitoring across AI services

Deployment & MLOps:

• Deploy AI services to cloud environments (AWS-first)

• Containerize applications using Docker and support CI/CD pipelines

• Apply MLOps best practices around evaluation, monitoring, rollback, and cost governance

Cross-Functional Collaboration:

• Work closely with product managers, frontend engineers, and data teams

• Translate business requirements into robust technical implementations

• Participate in architecture reviews and technical decision-making

Required Qualifications:

• Strong backend engineering experience with Python

• Hands-on experience building APIs using FastAPI

• Practical experience developing applications using Large Language Models (LLMs)

• Proven experience building generative AI or RAG-based systems

• Solid understanding of RESTful API design, service architecture, and best practices

Preferred Qualifications (Bonus Points):

• Experience deploying systems on AWS, GCP, or Azure

• Familiarity with LangChain, LlamaIndex, LangGraph, or CrewAI

• Experience with Docker, Kubernetes, and CI/CD pipelines

• Familiarity with vector databases (Pinecone, Weaviate, Qdrant, Chroma, OpenSearch)

• Experience with SQL and/or NoSQL databases

• Exposure to voice AI or real-time systems

What We Offer:

• Competitive salary and equity package

• Comprehensive health, dental, and vision insurance

• Flexible time off and remote work options

• The opportunity to work on challenging problems at the intersection of AI and technology

• A collaborative and innovative work environment

How to Apply:

Please send your resume to: jawaria@cognilium.ai

Or fill the application form: https://forms.gle/aeG8UFEv9Qo1Dgg76