Agent Capabilities: Design structured planning, self-correction/reflection loops, tool-calling mechanisms, memory management, and dynamic routing architectures
Prompt Engineering & Alignment: Develop advanced prompt engineering strategies (e.g., Chain-of-Thought, ReAct, directional stimulus prompting, few-shot conditioning) ensuring low latency, structured JSON outputs, and guardrails against hallucination
RAG & Information Retrieval Architecture
Advanced RAG Pipelines: Design, benchmark, and optimize enterprise-grade RAG systems implementing semantic search, hybrid retrieval (dense + sparse keyword matching), re-ranking, contextual chunking, and query decomposition
Vector Data Engineering: Configure, scale, and manage vector databases (e.g., Milvus, Pinecone, Qdrant, Chroma, PGVector, or AWS OpenSearch) for high-dimensional embedding retrieval
NLP & Embeddings: Benchmark, fine-tune, or calibrate state-of-the-art embedding models, tokenizers, and domain-adapted text representation pipelines
Productionization, MLOps & LLM Observability
LLM Evaluation & Observability: Establish rigorous evaluation frameworks (groundedness, context relevance, faithfulness) and trace agent executions using platforms such as LangSmith, Langfuse, or TruLens
System Design & API Integration: Collaborate on clean system design to serve agentic workflows via modern backend interfaces and microservices
Continuous Improvement: Implement automated testing suites to evaluate model drift, prompt regression, and agent task completion reliability across model upgrades
Requirements
Core Experience: 5+ years of total software/machine learning engineering experience, with at least 2 years of focused, hands-on experience building and deploying Generative AI and LLM applications in production
Programming & CS Foundations: Advanced proficiency in Python (async programming, data structures, profiling, and package ecosystems)
Generative AI & NLP: Deep hands-on experience with modern LLM APIs, foundation model ecosystems, transformer architectures, and classical NLP techniques
Agent Orchestration Frameworks: Proven production track record using LangGraph, LangChain, or CrewAI to build multi-step, tool-augmented, or stateful agent systems
RAG & Vector Search: Strong working knowledge of indexing, embedding generation, chunking strategies, and vector databases (e.g., Pinecone, Milvus, Qdrant, OpenSearch, PGVector)
Prompt Engineering: Demonstrated expertise in production-grade prompt templates, few-shot prompting, output parsing, schema enforcement (Pydantic), and safety guardrails
Desirable
Backend & System Design: Experience building microservices and RESTful/streaming endpoints using FastAPI or modern async frameworks
LLMOps & Tracing: Practical experience with evaluation and tracing suites like LangSmith, Langfuse, Arize Phoenix, or OpenTelemetry
Cloud & DevOps: Familiarity with AWS services (e.g., Bedrock, SageMaker, ECS, Lambda, S3), containerization with Docker, and orchestration with Kubernetes
Software Quality & CI/CD: Experience building automated CI/CD pipelines, static code analysis, and testing frameworks (pytest)
Education: Bachelor’s or Master’s degree in Computer Science, Data Science, AI/ML, Mathematics, or a related quantitative field
Opportunity to build cutting-edge agentic AI systems that drive measurable real-world outcomes
Collaborative engineering culture focused on modern AI paradigms, autonomous agents, and production experimentation
Competitive compensation, comprehensive benefits, and dedicated support for continuous technical upskilling and AI certifications
What’s in it for you?
Strong community: Work alongside top professionals in a friendly, open-door environment
Growth focus: Take on large-scale projects with a global impact and expand your expertise
Tailored learning: Boost your skills with internal events (meetups, conferences, workshops), Udemy access, language courses, and company-paid certifications
Endless opportunities: Explore diverse domains through internal mobility, finding the best fit to gain hands-on experience with cutting-edge technologies
Care: We’ve got you covered with company-paid medical insurance, mental health support, and financial & legal consultations
About us
At Ciklum, we are always exploring innovations, empowering each other to achieve more, and engineering solutions that matter. With us, you’ll work with cutting-edge technologies, contribute to impactful projects, and be part of a One Team culture that values collaboration and progress.
India is a strategic innovation hub for Ciklum, with growing teams in Chennai and Pune leading advancements in EdgeTech, AR/VR, IoT, and beyond. Join us to collaborate on game-changing solutions and take your career to the next level.
Explore, empower, engineer with Ciklum!
Interested already? We would love to get to know you! Submit your application. We can’t wait to see you at Ciklum.
#LI-GP1
