AI Software Engineer at S&P Global Market Intelligence

Join S&P Global Market Intelligence as an AI Software Engineer and play a pivotal role in designing and developing cutting-edge agentic AI platform components. This exciting opportunity is available in Hyderabad and Gurugram.

Key Responsibilities

• Design and build agentic AI platform components, including agents, tools, workflows, and integrations with internal systems.
• Implement comprehensive observability across the AI lifecycle, encompassing tracing, logging, metrics, and evaluation pipelines to monitor agent quality, cost, and reliability.
• Translate complex business problems into practical agentic AI solutions through close collaboration with product managers, subject matter experts, and platform teams, focusing on data, model, and orchestration requirements.
• Develop and maintain robust data pipelines, features, and datasets essential for the training, evaluation, grounding, and safety of LLM-based agents.
• Lead experimentation and benchmarking efforts, including testing of prompts, models, and agent workflows, followed by rigorous analysis of results to drive iterative improvements.
• Implement critical guardrails, safety checks, and policy controls across prompts, tool usage, access, and output filtering to ensure secure and compliant operations.
• Create essential documentation, runbooks, and best practices, while also mentoring peers on agentic AI patterns, observability-first engineering principles, and data/ML hygiene.

Core Skills Required

• Proficiency in Python programming (preferred) or equivalent languages.
• A strong understanding of LLM / GenAI fundamentals, including prompting, embeddings, vector search, RAG, and basic agentic patterns such as tool use, planning, and orchestration.
• Experience in managing production systems or data pipelines on cloud platforms like AWS, Azure, or GCP, leveraging containers, serverless architectures, and managed storage/services.
• Hands-on familiarity with observability tools such as OpenTelemetry, Prometheus, Grafana, ELK, and others, across logs, metrics, and traces.
• Comfort in working with both structured and unstructured data, with strong SQL skills and experience using frameworks like Pandas, Spark, or dbt.
• The ability to critically reason about trade-offs related to reliability, performance, and cost.
• Excellent collaboration and communication skills, with the capacity to articulate complex concepts to diverse teams including platform, product, data, security, and compliance.

Qualifications

• 1 to 3 years of experience in software engineering, data engineering, ML engineering, data science, or MLOps roles.
• A Bachelor's or Master's degree in Computer Science, Engineering, Data Science, or equivalent practical experience.
• Experience with CI/CD pipelines, code reviews, and modern engineering best practices.
• Nice to Have: Exposure to agentic AI frameworks (e.g., LangChain, LangGraph, OpenAI Agents) and experience with LLM observability or evaluation frameworks, or prior work on production LLM/agent systems.

What We're Looking For

Beyond technical skills and experience, we seek engineers who:

• Build for Scale: Approach system design with a platform-building mindset, creating solutions that benefit multiple teams and future use cases.
• Lead with Observability: Prioritize instrumentation, utilize data for debugging, and develop dashboards that provide clear insights into system behavior.
• Ship Safely: Consistently implement guardrails and validations before deployment, ensuring secure and reliable releases.
• Make Thoughtful Trade-offs: Clearly articulate and justify decisions concerning cost, quality, latency, and reliability.
• Own the End-to-End Stack: Navigate seamlessly across data pipelines, agent logic, infrastructure, and production monitoring.
• Learn Through Experimentation: Foster a culture of testing ideas, analyzing failures, iterating rapidly, and pursuing continuous improvement.
• Communicate with Impact: Effectively explain complex AI concepts in accessible, business-relevant terms to both technical and non-technical audiences.
• Stay Ahead of the Curve: Actively explore and integrate emerging technologies and capabilities in the AI space.