Senior ML Engineer - Agentic AI

About the role

You'll be joining a collaborative, fast-moving team of data scientists, AI engineers, machine learning engineers, and data engineers who work together to tackle complex, high-impact problems at the intersection of AI and enterprise software. We operate with a genuinely agile mindset - shipping iteratively, challenging assumptions, and staying close to the cutting edge. The team is proactive about research, consistently evaluating and adopting state-of-the-art methodologies, and we encourage everyone to experiment, share findings, and bring new ideas to the table. If you thrive in an environment where intellectual curiosity is the norm and the work is always evolving, you'll fit right in. Why Join SS&C SS&C combines proprietary technology with deep industry expertise to support complex financial and health care operations. Our teams design, implement, and operate solutions that help clients manage data, automate processes, and scale their businesses with confidence. You will work with industry experts, modern platforms, and evolving technologies, gaining exposure to real-world operational challenges and large-scale enterprise environments. How You Will Make an Impact Agent Design & Implementation Build and iterate on AI agents end-to-end - from defining goals, personas, and constraints to wiring LLM reasoning with tool execution. Design and build end-to-end autonomous AI agents that take user input, reason across multi-step workflows via large language models, and execute actions through APIs, tools, and enterprise data sources. Implement planning strategies including chain-of-thought, ReAct loops, and hierarchical task decomposition to enable agents to solve multi-step problems autonomously. Design and refine system prompts, few-shot examples, and guardrails that shape agent behavior, tone, and decision-making boundaries Implement advanced planning and memory systems - including chain-of-thought loops, ReAct patterns, deep plan and hierarchical planners - that allow agents to decompose complex tasks, retain context, and improve over time using vector database memory. Terminal-Based AI Coding & Development Work extensively inside AI-powered coding terminals (OpenCode, DeepCode, Hermes Agent) as both a user and a builder - understanding how these tools orchestrate LLM calls, file edits, and shell commands. Contribute to the development of custom coding agent workflows that automate code generation, review, refactoring, and testing tasks. Evaluate and benchmark terminal agent behaviors: accuracy of code edits, hallucination rates, context utilization, and multi-file reasoning. Model Context Protocol (MCP) & Tool Integration Build and extend MCP servers (using FastMCP and similar frameworks) that expose internal tools, databases, and APIs as structured capabilities for agents. Design tool schemas, descriptions, and invocation patterns that LLMs can reliably discover and call. Integrate agents with external services - REST APIs, vector stores, graph databases, and internal SDKs - through well-defined MCP interfaces. CI/CD Pipeline Containerize and deploy production-grade agent services on Kubernetes, including building CI/CD pipelines, autoscaling configurations, and infrastructure-as-code with Docker and Helm. Define evaluation frameworks and observability pipelines (LangFuse) to measure agent performance - covering retrieval accuracy, tool-selection correctness, and hallucination rate - and use insights to drive continuous improvement via A/B testing and audits. Embed security and compliance into every layer: IAM token, Connect tokens, prompt injection mitigations, etc. Partner closely with data scientists, ML engineers, product managers, and security teams to translate complex business needs into robust, scalable agentic solutions. LLM Experimentation & Evaluation Experiment with a range of open-source LLMs (Qwen, DeepSeek, finetune domain-specific models) to evaluate reasoning quality, latency, cost, and tool-use reliability. Explore inference optimizations such as speculative decoding, constraint decoding, structured outputs, and router-mode orchestration . Build and run evaluation pipelines to measure retrieval accuracy, tool-selection precision, hallucination rate, and end-to-end task completion. Memory & Retrieval Systems Integrate agents with a broad ecosystem of external systems: vector stores (PgVector, Milvus), relational and graph databases, REST APIs, and internal microservices, all managed through secure, least-privilege access patterns. Design