Leads the team this role joins
Decides on early hires
Runs hiring at the company
From your own Gmail and LinkedIn.
About the role
Redwood Software is hiring a Software Engineer in Hyderabad, India, to lead the design and delivery of production-grade AI and agentic capabilities that can be reused across its products. The role suits engineers who have owned production systems and who can shape technical direction while still writing a lot of code themselves. Much of the work goes into shared AI infrastructure, developer tooling, and platform services used by enterprise automation products that run across ERP, cloud, and on-premises environments. You will often work on problems where requirements and approaches are not yet settled, and you will coordinate with several teams to get them into production.
What you’ll do
- Ship sophisticated services, multi-step agent workflows, and platform capabilities shared across Redwood's products.
- Assemble agent systems from reasoning, tool invocation, retrieval, memory, policy enforcement, and human review steps.
- Define how AI quality is measured and monitored, including model selection, fallback paths, and recovery from failure.
- Guide delivery across a group of engineers and align dependencies with product and platform owners.
- Examine designs and code for scale, security, speed, dependability, upkeep, and cost.
- Investigate difficult production incidents and ship changes that stop them from coming back.
- Build reusable toolkits, reference implementations, and engineering standards that speed up other teams.
- Work with product, architecture, security, data, and operations to shape durable platform answers to business needs.
- Assess new AI technologies and recommend adoption based on evidence, enterprise constraints, and business value.
- Take ownership of complex systems that affect your own team and several partner groups.
- Reduce technical and operational risk across multiple services or product areas.
What they’re looking for
- Four or more years of professional software engineering, including ownership of production systems.
- Advanced skill in Python, Java, or another production language.
- Strong background in distributed systems, APIs, integrations, cloud services, and production applications.
- Hands-on experience delivering generative AI or agentic systems into production.
- Experience with agent orchestration, tool calling, retrieval-augmented generation, prompt management, or model integration.
- Experience implementing AI evaluation, tracing, monitoring, security controls, and reliability mechanisms.
- Solid understanding of architecture, automated testing, CI/CD, cloud deployment, and production operations.
- Ability to lead complex technical work while staying hands-on.
- Sound technical judgement and clear written and verbal communication.
Nice to have
- Experience with LangGraph, AutoGen, Semantic Kernel, or a custom agent orchestration framework.
- Working knowledge of transformer architectures, fine-tuning, inference strategies, or model evaluation.
- Experience with vector databases, model gateways, prompt lifecycle platforms, or AI observability tools.
- Experience with Kubernetes, Docker, messaging systems, event-driven architectures, or distributed systems.
- Experience with enterprise middleware, workflow orchestration, ERP, or integration platforms.
- Experience building internal platforms, developer tools, or reusable capabilities for engineering teams.
- Exposure to regulated, security-sensitive, or high-availability enterprise environments.
Skills
Questions about this role
Where is this role based?
The role is listed in Hyderabad, Telangana, India.
How many years of experience do I need?
The posting asks for four or more years of professional software engineering experience, including ownership of production systems.
Is LangGraph experience required?
No. LangGraph, AutoGen, and Semantic Kernel experience is listed as a nice-to-have, not a requirement.