Senior Product Engineer, Agent Systems

About the role

This role builds the agent fleet that performs enterprise modernization, operating under governed autonomy from shadow to autonomous stages. You work as a product engineer, where the agents you ship are the product itself.

Software engineers turn product ideas into working code. Engineers work in small teams, review each other's work, and ship in small batches. Most teams follow agile practices such as sprints and daily standups. Engineers also write tests, fix bugs, and improve performance. The field values clear communication as much as technical skill. Engineers spend part of every week on planning, code review, and debugging, not just writing new code. The ability to explain a technical decision in plain words separates strong engineers from the rest.

Key facts

What you'll do

The agent fleet ingests legacy estates and converts them into governed AI agents that execute modernization. Each agent leverages the Code Intelligence Graph to understand systems and produces behavior-equivalence proof that audit chains remain intact for regulated enterprises.

You construct parsers, extractors, synthesizers, and verifiers that operate on the persistent semantic model of the customer estate. These components translate legacy code into workflows and validate correctness under governed autonomy through shadow, supervised, and autonomous stages.

Python orchestration connects frontier foundation models via the Aedeon Decision Model to deliver regulated modernization workloads. The output aligns with the broader product team's release discipline, ensuring consistency and reliability across the fleet.

Requirements

The posting states a bachelor's degree requirement. You hold a degree as stated in the original listing.

You write strong Python and deeply learn agent frameworks instead of treating them as buzzwords.

You ensure new behavior matches legacy behavior for regulated customers while preserving intact audit chains.

You work through shadow, supervised, and autonomous workflow stages under governed autonomy.

Practical notes

The role is fully remote but based in Mumbai, MH, and operates within the release discipline of the product team.

Typical interview steps

Hiring for engineering roles usually starts with a recruiter screen, followed by one or two technical rounds. Candidates often solve a coding problem, discuss past projects, and answer system design questions. Some loops include a take-home task. Final rounds typically cover team fit and give candidates a chance to ask questions. Interviewers look for how you break down an unfamiliar problem, not just whether you reach the answer. Practicing a few problems aloud and reviewing your own past projects are the best preparation.

Good to know

Agent-native modernization uses AI to convert enterprise systems into governed agents.

A persistent semantic model of the customer estate guides modernization decisions and maintains context.

Behavior-equivalence proof ensures regulated compliance during system transformation.

This role concentrates on product engineering where the agents themselves are the delivered product.

Questions to ask

Worth asking in any interview: how the team measures success, who the role works with daily, what the onboarding looks like, and what the company is trying to achieve this year. Asking what past hires did well is a strong final question. Keep the list short and pick the questions that matter most to you.

Career growth

Engineering careers usually progress from individual contributor to senior, staff, and principal levels. Some engineers move into management and lead teams of five to twenty people. Others stay on the technical track. Growth follows demonstrated impact, not tenure alone. A typical engineering ladder has clear levels with defined expectations for scope, quality, and mentorship. Moving up usually requires owning outcomes end to end rather than completing assigned tickets.

About the company

Mactores is the agent-native AWS modernization firm. We ship AWS modernization to production in weeks, data platforms migrated, legacy applications and databases refactored, AI agents running against real data, for mid-market and lower-enterprise companies in financial services, healthcare and life sciences, internet and software, manufacturing, and TMEGS.