21 days ago
Pune, IndiaStaff+
Responsibilities
- Architect and deliver enterprise-grade Generative AI, LLM, and agentic systems, including copilots, domain assistants, and multi-agent workflows.
- Design agent planning, orchestration, review, evaluation, execution, human-in-the-loop controls, safety mechanisms, and monitoring.
- Translate business and investment challenges into scalable architectures and production-ready AI services.
- Build RAG solutions using semantic and hybrid search, embeddings, knowledge bases, metadata enrichment, reranking, and retrieval-quality optimization.
- Establish LLMOps capabilities for prompt management, model evaluation, observability, performance and cost monitoring, testing, validation, and responsible AI.
- Lead hands-on full-stack, backend, data, cloud, and distributed-systems engineering using modern frontend and backend technologies.
- Design predictive and analytical models for classification, ranking, recommendation, and forecasting, including explainability and robust validation.
- Define technical strategy, architecture, reusable engineering patterns, standards, and working practices for AI-powered products and platforms.
- Guide prototypes from proof of concept through enterprise deployment and measurable business outcomes.
- Mentor engineers, strengthen engineering practices, manage delivery dependencies and trade-offs, and communicate technical concepts to technical and non-technical stakeholders.
Requirements
- Extensive hands-on software engineering experience delivering enterprise-scale distributed applications and production-grade AI or Generative AI solutions.
- Deep expertise in ReactJS and TypeScript, with strong Python or Java engineering skills and experience designing APIs, microservices, and asynchronous applications.
- Experience with BigQuery, PostgreSQL, cloud-native architectures, Git-based development, CI/CD, Docker, Kubernetes, infrastructure as code, observability, and automated testing.
- Practical expertise in LLM applications, AI agents, RAG architectures, vector databases, semantic or hybrid search, model evaluation, and LLMOps.
- Experience with orchestration, evaluation, and observability tools such as LangGraph, LangChain, Semantic Kernel, MLflow, LangSmith, or OpenTelemetry.
- Grounding in machine learning, feature engineering, model explainability, analytical modeling, and relevant Python machine learning libraries.
- Strong understanding of financial markets and investment products is highly desirable, including asset management, ETFs or mutual funds, and investment performance and risk metrics.
- Demonstrated technical leadership, including setting direction, mentoring engineers, driving accountability, and leading delivery across the engineering lifecycle.
- Strong stakeholder management, communication, collaboration, problem-solving, judgment, and ability to balance delivery speed, quality, risk, maintainability, and scalability.
- Bachelor’s degree in Computer Science, Engineering, Science, or a related discipline, or equivalent professional experience.
Tech Stack
DockerFastAPIGitGoogle BigQueryJavaKubernetesMLflowPostgreSQLPythonPyTorchReactscikit-learnSpring BootTerraformTypeScript
Categories
About DWS Group
DWS Group is a global asset manager that provides active, passive (Xtrackers ETFs), and alternative investment products for institutions, financial intermediaries, and individual investors. It earns management and performance fees across mutual funds and bespoke mandates, managing over €1 trillion in assets. Founded in 1956 and headquartered in Frankfurt, DWS is publicly listed in Germany and remains majority-owned by Deutsche Bank.