Senior AI Developer Remote | Full-Time | India Based
PRIME BPM is an AI-powered, end-to-end Business Process Management Software designed to help you simplify and fast-track process mapping, analysis and improvement. Combining the best-of-breed inbuilt methodology with next-gen AI agents, PRIME BPM removes the burden of manual documentation and analysis—enabling teams to move faster to real business transformation and delivering measurable results. Built with an intuitive, user-friendly interface, PRIME BPM is designed to meet unique requirements of both process experts and business users. With over a decade of experience, PRIME BPM has empowered leading public and private sector organisations, including Pfizer, Airbus, Coca-Cola, CBRE, Vodafone, Flight Centre, Rolls-Royce, and many others, drive business transformation and operational excellence.
To be able to engage and retain such prestigious customers, it is easy to understand that we have a high-performance culture. Our team is made up of talented and passionate members who are supported by processes, systems, KPI’s and metrics.
We work in a fast-paced, structured and organised environment and are on a super exciting journey together. We are virtually connected throughout the day and our multicultural team oozes positive vibes!
Job Summary:
We are seeking a Senior AI Agent Systems Engineer to build autonomous enterprise AI coworkers and development agents. The ideal candidate will have a deep understanding of LLMs, natural language processing (NLP), agent orchestration frameworks, and strong software engineering skills. You will be responsible for maintaining and optimizing existing AI solutions while also designing and implementing new agents and workflows that integrate with enterprise data sources, APIs, and business systems.
Key responsibilities include:
- Building AI agents capable of executing autonomous workflows based on knowledge and understanding.
- Developing agents that can interact with external and internal / systems, APIs, and enterprise tooling.
- Implementing safe autonomous execution and human-in-the-loop approval systems.
- Maintaining, monitoring, and improving existing AI agents and applications to ensure reliability, performance, and scalability.
- Designing and building scalable custom AI agents using LLMs (e.g., OpenAI GPT, Claude, Mistral, Locall LLMs, Llama, etc.) and orchestration tools.
- Architecting agent workflows to reason, plan, and act on user queries across structured and unstructured data sources.
- Integrating AI agents with APIs, databases, RAG pipelines, vector databases (e.g., FAISS, Weaviate, Pinecone), and business systems.
- Optimizing prompt engineering, agent memory, context handling, and dynamic task chaining.
- Work on exciting ideas like coordinator agents, specialized worker agents, supervisor-reviewer patterns, collaborative agent systems, memory sharing between agents, and distributed task execution
- Collaborating with cross-functional teams (engineering, product, data science) to enhance existing AI solutions and build new ones aligned with business goals.
- Conducting experiments, debugging, and evaluations to validate and improve the performance and usability of AI agents.
- Staying up to date with the latest in LLM technologies, open-source frameworks (e.g., LangChain, Semantic Kernel, Haystack), and emerging AI trends.
- Ensuring security, compliance, and ethical use of AI systems in production environments.
What We’re Looking For:
- 5+ years of experience in software engineering, with at least 2+ years in LLM-based or agent-based AI systems.
- Proven experience maintaining, debugging, and enhancing production-grade AI systems.
- Strong focus on observability, token/cost optimization, evaluation frameworks, guardrails, hallucination mitigation, scaling AI infrastructure, and latency optimizations.
- Strong knowledge of Python and experience with frameworks such as LangChain, LlamaIndex, Haystack, or Semantic Kernel.
- Hands-on experience with LLMs (OpenAI, Azure OpenAI, Anthropic, Cohere, etc.) and prompt engineering.
- Familiarity with retrieval-augmented generation (RAG), embeddings, vector databases, and hybrid search strategies.
- Proficiency in integrating agents with APIs, databases (SQL/NoSQL), and cloud platforms (AWS, Azure, GCP).
- Solid software engineering fundamentals: Git, CI/CD pipelines, testing frameworks, and monitoring tools.
- Understanding of NLP, transformers, and ML pipelines.
What you will build
- AI software engineering agents
- Autonomous workflow agents
- Multi-agent collaboration systems
- AI copilots for enterprise workflows
- RAG and enterprise knowledge systems
- AI-powered automation and orchestration platforms
- Human-in-the-loop AI systems
- Long-running memory-enabled AI agents
Preferred skills and experience:
- Experience maintaining and extending copilots, autonomous agents, or task-specific chatbots.
- Familiarity with Kubernetes, Docker, scalable API services, FastAPI, Redis, Celery / async workers, Azure OpenAI, vector DBs, OpenTelemetry / Langfuse / Phoenix, MCP (Model Context Protocol), CrewAI / AutoGen / LangGraph, browser automation, Playwright, GitHub API integrations.
- Background in data privacy, security, and compliance in AI deployments.
- Contributions to open-source AI projects or research publications.
Preferred skills and experience:
- Remote role (work from home)
- Working hours: 12:00 PM – 09:00 PM IST Monday to Friday
Equipment Requirement:
- Must have a reliable and well-maintained laptop with stable internet connectivity.
Benefits:
- An excellent salary.
- A team environment that oozes positive vibes.
- International client exposure.
- A robust onboarding and induction program.
- Solid systems and processes in place for ease of working.
- An organizational culture invested in ongoing learning.
- Initial and ongoing support from a great team.
- Work from home.
- Autonomy, mastery, and purpose!