About Gurucul

Security teams today are trying to keep watch over a world that keeps expanding, with machines and AI agents multiplying faster than anyone can hire analysts to watch them, and the attacks aimed at that world move faster every year than most tools were ever built to catch. Gurucul’s mission comes out of that gap: give defenders a system that sees a threat the moment it starts forming, whether it comes from a person, a machine, or an AI agent, so a risk climbing quietly over days turns into something an organization can act on long before anything is lost.

Building that takes fusing behavioral models with deterministic detections and a real-time graph that connects signals analysts would otherwise have to piece together by hand, and it means working alongside people who have spent a decade refining behavioral analytics nobody else in the industry has matched, solving problems that show up in production at Fortune 500 companies, Global 5000 enterprises, and governments who are counting on getting ahead of what’s coming for them.

That work has already earned Gurucul recognition as a Leader in the 2025 Gartner Magic Quadrant for SIEM and as Overall Leader in KuppingerCole’s Intelligent SIEM Leadership Compass, the kind of validation that comes from actually cutting data costs, false positives, and response times at scale rather than just claiming to.

If spending your career on something that actually changes how fast defenders can see and respond to what’s coming sounds like the kind of work you want, this is the team doing it, and we’re hiring..

Role Summary

Gurucul is seeking an experienced AI Engineer to be part of our talented team of developers. The ideal candidate will have a strong background in software development using AI tech stack.

Required Responsibilities:

- Be part of the SCRUM team to work on AI development stories to add on new AI features to the product
- Work closely with product, data, and backend engineering teams




- Translate business requirements into AI system designs
- Build Retrieval-Augmented Generation pipelines using LlamaIndex, LangChain, etc.
- Design chunking, embedding, and retrieval strategies for knowledge bases
- Integrate vector databases (Pinecone, Weaviate, Chroma, pgvector)
- Build and ship production-grade LLM-powered features (chatbots, copilots, agents)
- Design prompt engineering strategies and manage prompt versioning
- Develop multi-agent systems and autonomous workflows
- Integrate AI capabilities via REST/GraphQL APIs
- Work with LLM provider APIs (OpenAI, Anthropic, Groq, Cohere, etc.)
- Build scalable inference endpoints and manage latency/throughput tradeoffs
- Write, test, and optimize system prompts and few-shot examples
- Manage context window efficiently for long-context tasks
- Build guardrails and safety layers around model outputs
- Stay current with AI/ML research and evaluate current models/tools
- Rapidly prototype proof-of-concepts and assess feasibility
- Contribute to internal knowledge sharing and documentation
- Implement prompt injection defenses and input/output sanitization
- Ensure compliance with data privacy regulations (GDPR, HIPAA where applicable)
- Apply responsible AI principles — bias detection, fairness, transparency

Required Qualifications

- BE/ME/B.Tech/M.Tech degree in Computer Science, Engineering or related discipline
- Strong communication and interpersonal skills
- Good team player
- Self and quick learner
- Excellent problem-solving and decision-making skills




- Minimum of 3+ years of experience in AI related application development and overall experience of 8 to 10 in enterprise application development
- Ability to come up with solutions to business problems
- Ability to drive architecture decisions by strong technical evidences
- In-depth understanding and hands on experience on with core programming- Strong Python skills or else Java is big plus , SQL and API development, FastAPI or Flask for backend services, some exposure to TypeScript/Node.js is a plus
- Hands-on experience with frameworks such as LangChain, LangGraph, LlamaIndex, CrewAI, AutoGen, Temporal, Ray
- Experience working with models/platforms like OpenAI Platform, Anthropic Claude, Google Gemini,Open-source models like Llama or Mistral
- Good exposure to Prompt engineering, Context management, Model evaluation, Cost/latency optimization, Fine-tuning
- Mandatory skillset on RAG & Vector Databases typical tools include -Pinecone, Weaviate, Qdrant, Elasticsearch/OpenSearch
- Experience on Chunking strategies, Embeddings, Hybrid search, Reranking, Knowledge retrieval pipelines
- Good hands on with Agentic AI / Workflow Orchestration and working experience on Multi-agent systems, Autonomous workflows, Planner-executor architectures, Human-in-the-loop workflows, Long-running AI processes
- Experience with NLP libraries such as spaCy or NLTK
- NLP familiarity with text preprocessing and feature extraction
- Understanding of transformer-based models

Preferred Qualifications (Nice-to-Have)

- Nice to have exposure on Deployment & Infrastructure with Docker, Kubernetes, CI/CD pipelines, Cloud platforms like-AWS, Google Cloud, Microsoft Azure
- Nice to have awareness on LLMOps / Observability tools -LangSmith, MLflow, Weights & Biases

Location

Pune, India

Equal Opportunity Employer

Gurucul Solutions, LLC is an equal opportunity employer. We celebrate diversity and are committed to creating an inclusive environment for all employees.

To apply:

Please send resumes to [email protected] for consideration.

📌 Senior AI Engineer (Pune)
🏢 Gurucul
📍 Pune