AI/LLM Developer
Role details
Job location
Tech stack
Job description
-
Data Analysis and Modeling: Leveraging advanced analytics and machine learning techniques to extract actionable insights from data, enabling data-driven decision-making for the client.
-
Model Development: Creating predictive models and AI-driven solutions that optimize client services, enhance personalization, and improve overall client experiences.
-
Continuous Improvement: Iterating on models and algorithms to adapt to changing client needs and data trends, ensuring that services evolve to meet evolving expectations.
-
Data Security and Ethics: Upholding data privacy standards and ethical AI practices to build trust with clients and protect sensitive information.
-
Cross-functional Collaboration: Collaborating with cross-functional teams to integrate AI/ML solutions seamlessly into client services, aligning technology with business goals.
-
Innovation: Staying at the forefront of AI and ML advancements to identify opportunities for innovation and provide clients with cutting-edge, competitive services.
Responsibilities:
- Extend and harden RAG pipelines, retrieval strategies, and embedding workflows.
- Design, implement, and productionize agent architectures that orchestrate between RAG, structured queries, and external actions (APIs, PPT generation).
- Finetune and evaluate LLMs; implement model selection, prompt engineering, and safety/guardrails.
- Build/maintain endpoints and tooling for model serving, versioning, and observability.
- Collaborate with SQL engineers to safely access structured data; design retrieval interfaces and templates.
- Implement testing, monitoring, and metrics (latency, accuracy, hallucination rates, cost).
- Participate in architecture decisions for cost/perf tradeoffs and vendor selection.
Requirements
- Hands-on experience building RAG pipelines and agentic systems in production.
- Practical experience fine-tuning LLMs or applying model-adaptation techniques.
- Experience with at least one LLM orchestration library (e.g., LangChain, LlamaIndex, or equivalent) and ability to explain deep implementation details.
- Strong software engineering skills (Python preferred) and API design experience.
- Ability to explain concrete projects: architecture, why tools chosen, dataset preparation, evaluation metrics, and deployment details., * Experience integrating LLMs with databases and ability to implement secure structured-data retrieval.
- Familiarity with embedding stores / vector DBs (e.g., Pinecone, Milvus, Weaviate, or Oracle embedding features).
- Knowledge of LLM safety, prompting strategies, retrieval augmentation, and hallucination mitigation.
- Experience with cloud model hosting, monitoring, cost optimization, and infra (K8s, serverless).
- Java experience is nice-to-have for interoperability but not required.